As multimedia content often contains noise from intrinsic defects of digital devices, image denoising is an important step for high-level vision recognition tasks. Although several studies have developed the denoising field employing advanced Transformers, these networks are too momory-intensive for real-world applications. Additionally, there is a lack of research on lightweight denosing (LWDN) with Transformers. To handle this, this work provides seven comparative baseline Transformers for LWDN, serving as a foundation for future research. We also demonstrate the parts of randomly cropped patches significantly affect the denoising performances during training. While previous studies have overlooked this aspect, we aim to train our baseline Transformers in a truly fair manner. Furthermore, we conduct empirical analyses of various components to determine the key considerations for constructing LWDN Transformers. Codes are available at https://github.com/rami0205/LWDN.

翻译：随着多媒体内容常因数字设备固有缺陷而产生噪声，图像去噪对于高级视觉识别任务至关重要。尽管已有研究利用先进的Transformer网络推动了去噪领域的发展，但这些网络在实际应用中内存占用过高。此外，针对Transformer的轻量级去噪（LWDN）研究尚显不足。为此，本文提供了七种用于LWDN的对比基线Transformer，作为未来研究的基础。我们还证明了训练过程中随机裁剪补丁的区域会显著影响去噪性能。尽管先前研究忽视了这一方面，我们致力于以真正公平的方式训练基线Transformer。此外，我们对不同组件进行了实证分析，以确定构建LWDN Transformer的关键考量因素。代码开源于https://github.com/rami0205/LWDN。